Data Augmentation Techniques for Extreme Wind Prediction Improvement

Authors

Marta Vega-Bayo

Antonio Manuel Gómez-Orellana

Víctor Manuel Vargas-Yun

David Guijo-Rubio

Laura Cornejo-Bueno

Jorge Pérez-Aracil

Sancho Salcedo-Sanz

Conference Proceedings

Bioinspired systems for translational applications: From robotics to social engineering

ISSN 1611-3349

Vol. 14675

Pages 303–313

Abstract

Predicting extreme winds (i.e. winds speed equal to or greater than 25 m/s), is essential to predict wind power and accomplish safe and efficient management of wind farms. Although feasible, predicting extreme wind with supervised classifiers and deep learning models is particularly difficult because of the low frequency of these events, which leads to highly unbalanced training datasets. To tackle this challenge, in this paper different traditional data augmentation techniques, such as random oversampling, SMOTE, time series data warping and multidimensional data warping, are used to generate synthetic samples of extreme wind and its predictors, such as previous samples of wind speed and meteorological variables of the surroundings. Results show that using data augmentation techniques with the right oversampling ratio leads to improvement in extreme wind prediction with most machine learning and deep learning models tested. In this paper, advanced data augmentation techniques, such as Variational Autoencoders (VAE), are also applied and evaluated when inputs are time series.

Keywords

data augmentation deep learning extreme wind speed classification machine learning

BibTex Citation

@inproceedings{Vega2024Data,
	author = {Vega-Bayo, Marta and G{\' o}mez-Orellana, Antonio Manuel and Vargas-Yun, V{\' i}ctor Manuel and Guijo-Rubio, David and Cornejo-Bueno, Laura and P{\' e}rez-Aracil, Jorge and Salcedo-Sanz, Sancho},
	booktitle = {Bioinspired systems for translational applications: From robotics to social engineering},
	doi = {10.1007/978-3-031-61137-7_28},
	year = {2024},
	pages = {303--313},
	title = {Data {Augmentation} {Techniques} for {Extreme} {Wind} {Prediction} {Improvement}},
	url = {https://link.springer.com/chapter/10.1007/978-3-031-61137-7_28},
	howpublished = {https://link.springer.com/chapter/10.1007/978-3-031-61137-7\textunderscore{}28},
	volume = {14675},
}

BibTex Unicode Citation

@inproceedings{Vega2024Data,
	author = {Vega-Bayo, Marta and Gómez-Orellana, Antonio Manuel and Vargas-Yun, Víctor Manuel and Guijo-Rubio, David and Cornejo-Bueno, Laura and Pérez-Aracil, Jorge and Salcedo-Sanz, Sancho},
	booktitle = {Bioinspired systems for translational applications: From robotics to social engineering},
	doi = {10.1007/978-3-031-61137-7_28},
	year = {2024},
	pages = {303--313},
	title = {Data {Augmentation} {Techniques} for {Extreme} {Wind} {Prediction} {Improvement}},
	url = {https://link.springer.com/chapter/10.1007/978-3-031-61137-7_28},
	howpublished = {https://link.springer.com/chapter/10.1007/978-3-031-61137-7\textunderscore{}28},
	volume = {14675},
}

APA Citation

Vega-Bayo, M., Gómez-Orellana, A. M., Vargas-Yun, V. M., Guijo-Rubio, D., Cornejo-Bueno, L., Pérez-Aracil, J., & Salcedo-Sanz, S. (2024). Data Augmentation Techniques for Extreme Wind Prediction Improvement. Bioinspired Systems for Translational Applications: From Robotics to Social Engineering, 14675, 303–313. https://doi.org/10.1007/978-3-031-61137-7_28

RIS Citation

TY  - CONF
AU  - Vega-Bayo, Marta
AU  - Gómez-Orellana, Antonio Manuel
AU  - Vargas-Yun, Víctor Manuel
AU  - Guijo-Rubio, David
AU  - Cornejo-Bueno, Laura
AU  - Pérez-Aracil, Jorge
AU  - Salcedo-Sanz, Sancho
C3  - Bioinspired systems for translational applications: From robotics to s
ocial engineering
DA  - 2024///
C2  - 2024
DO  - 10.1007/978-3-031-61137-7_28
ID  - temp_id_658429819778
SP  - 303-313
TI  - Data Augmentation Techniques for Extreme Wind Prediction Improvement
UR  - https://link.springer.com/chapter/10.1007/978-3-031-61137-7_28
VL  - 14675
ER  -

CV Citation

M. Vega-Bayo, A.M. Gómez-Orellana, V.M. Vargas-Yun, D. Guijo-Rubio, L. Cornejo-Bueno, J. Pérez-Aracil, S. Salcedo-Sanz (3/7). "Data Augmentation Techniques for Extreme Wind Prediction Improvement". Bioinspired systems for translational applications: From robotics to social engineering, pp. 303–313, 2024.